{"benchmark_id":"hle-verified","benchmark_name":"HLE-Verified","benchmark_description":"HLE-Verified evaluates multidisciplinary expert reasoning on a verified subset of Humanity's Last Exam.","max_score":1.0,"categories":["knowledge","reasoning"],"modality":"text","total_models":3,"entries":[{"rank":1,"model_id":"gemini-3.8-flash","model_name":"Gemini 3.8 Flash","organization_name":"Google","organization_id":"google","benchmark_score":0.549,"normalized_score":0.549,"verified":false,"self_reported":true,"provider_id":"google","input_cost_per_million":0.75,"output_cost_per_million":3.75,"speed_rps":null,"context_window":1048576,"release_date":"2026-09-02","announcement_date":"2026-09-02","multimodal":true,"param_count":null,"is_new":false},{"rank":2,"model_id":"gemini-3.7-flash","model_name":"Gemini 3.7 Flash","organization_name":"Google","organization_id":"google","benchmark_score":0.536,"normalized_score":0.536,"verified":false,"self_reported":true,"provider_id":"google","input_cost_per_million":0.75,"output_cost_per_million":3.75,"speed_rps":null,"context_window":1048576,"release_date":"2026-08-13","announcement_date":"2026-08-13","multimodal":true,"param_count":null,"is_new":false},{"rank":3,"model_id":"qwen3-max-thinking","model_name":"Qwen3 Max Thinking","organization_name":"Alibaba Cloud / Qwen Team","organization_id":"qwen","benchmark_score":0.376,"normalized_score":0.376,"verified":false,"self_reported":true,"provider_id":"deepinfra","input_cost_per_million":1.2,"output_cost_per_million":6.0,"speed_rps":null,"context_window":256000,"release_date":"2026-02-13","announcement_date":"2026-02-13","multimodal":false,"param_count":1000000000000,"is_new":false}]}